Related papers: ELSA: Exploiting Layer-wise N:M Sparsity for Visio…

Hybrid vision transformers combine the elements of conventional neural networks (NN) and vision transformers (ViT) to enable lightweight and accurate detection. However, several challenges remain for their efficient deployment on…

Vision-Language Models (VLMs) integrate information from multiple modalities and have shown remarkable success across various tasks. However, deploying large-scale VLMs in resource-constrained scenarios is challenging. Pruning followed by…

Model inversion, which aims to reconstruct the original training data from pre-trained discriminative models, is especially useful when the original training data is unavailable due to privacy, usage rights, or size constraints. However,…

Vision transformers (ViTs) inherited the success of NLP but their structures have not been sufficiently investigated and optimized for visual tasks. One of the simplest solutions is to directly search the optimal one via the widely used…

The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length…

Attention-based vision models, such as Vision Transformer (ViT) and its variants, have shown promising performance in various computer vision tasks. However, these emerging architectures suffer from large model sizes and high computational…

Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. However, when it comes to handling long token sequences, especially in dense prediction tasks that require…

Neural networks have achieved state of the art performance across a wide variety of machine learning tasks, often with large and computation-heavy models. Inducing sparseness as a way to reduce the memory and computation footprint of these…

As learned image compression (LIC) methods become increasingly computationally demanding, enhancing their training efficiency is crucial. This paper takes a step forward in accelerating the training of LIC methods by modeling the neural…

This paper explores the feasibility of finding an optimal sub-model from a vision transformer and introduces a pure vision transformer slimming (ViT-Slim) framework. It can search a sub-structure from the original model end-to-end across…

Long Short-Term Memory (LSTM) has achieved state-of-the-art performances on a wide range of tasks. Its outstanding performance is guaranteed by the long-term memory ability which matches the sequential data perfectly and the gating…

Our work tackles the computational challenges of contrastive learning methods, particularly for the pretraining of Vision Transformers (ViTs). Despite the effectiveness of contrastive learning, the substantial computational resources…

Training large transformers is slow, but recent innovations on GPU architecture give us an advantage. NVIDIA Ampere GPUs can execute a fine-grained 2:4 sparse matrix multiplication twice as fast as its dense equivalent. In the light of this…

Neural Architecture Search (NAS) has shown promising performance in the automatic design of vision transformers (ViT) exceeding 1G FLOPs. However, designing lightweight and low-latency ViT models for diverse mobile devices remains a big…

Semi-structured N:M sparsity and low-bit quantization (e.g., 1.58-bit BitNet) are two promising approaches for improving the efficiency of large language models (LLMs), yet they have largely been studied in isolation. In this work, we…

Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and distillation, semi-structured sparsity, which can nearly halve…

Sparse Matrix-Vector Multiplication (SpMV) is a fundamental operation in the inference of sparse Large Language Models (LLMs). Because existing SpMV methods perform poorly under the low and unstructured sparsity (30-90%) commonly observed…

In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…

The energy consumption of large-scale ML models is dominated by data movement, shuffling billions of parameters across memory hierarchies and data centers. Sparsification offers a principled way to mitigate these costs by pruning redundant…

In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We find that attention weights can be separated into two parts:…